| 摘要 |
This method is for monitoring the condition of machines where the measurements are performed on a number of machines or machine parts to obtain quantities descriptive of the condition of the machines. The characteristics or symptoms related to the operation or condition of the machine concerned are derived from the measured quantities and/or the measured quantities are directly regarded as characteristics. A characteristic vector, i.e. syndrome describing the current operational state of the machine is generated from characteristics descriptive of the same operational state of the machine. Characteristic vector categories are formed from characteristic vectors describing the same operational state so that each characteristic in each characteristic vector category has an allowed range of variation. A database is created in which are stored characteristic vector categories describing different operational states of the machines together with the allowed ranges of variation of the characteristics and to analyze the operation of a machine, a characteristic vector describing its current operational state is generated from the quantities measured from it, and the characteristic vector is compared to the database containing characteristic vector categories describing different operational states of machines. An alarm is activated if the characteristic vector being compared corresponds to a characteristic vector category describing an operational state requiring an alarm or if no characteristic vector category corresponding to the characteristic vector can be found in the database, in which case the characteristic vector is added to a characteristic vector category existing in the database, thereby expanding the allowed ranges of variation of the characteristics in the characteristic vector category or a new characteristic vector category is generated on the basis of the characteristic vector.
|
